Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2246. Min Range: -1.2246

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1193344 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.2246. Min Range: -1.2246

Max Act: 1.2179. Min Act: -0.0000

Data Index: 56716 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1149087 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.2246. Min Range: -1.2246

Max Act: 1.0362. Min Act: -0.0000

Data Index: 538663 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.2246. Min Range: -1.2246

Max Act: 1.0394. Min Act: -0.0000

Data Index: 852296 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1171598 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8359. Min Act: -0.0000

Data Index: 69837 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8596. Min Act: -0.0000

Data Index: 662289 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8380. Min Act: -0.0000

Data Index: 226005 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1351536 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8889. Min Act: -0.0000

Data Index: 782293 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8528. Min Act: -0.0000

Data Index: 884609 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8759. Min Act: -0.0000

Data Index: 16459 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8780. Min Act: -0.0000

Data Index: 540256 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8293. Min Act: -0.0000

Data Index: 493896 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1194021 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1171254 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8155. Min Act: -0.0000

Data Index: 700825 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.8191. Min Act: -0.0000

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.2246. Min Range: -1.2246

Max Act: 0.7869. Min Act: -0.0000

Data Index: 991939 (C4 (Web Text))

Max Activating Token Index: 1019